Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques

In the present study, the utilization of machine learning algorithms (MLAs) is proposed for the prediction of the heat transfer coefficient and pressure drop in horizontal, vertical, and inclined tubes during flow boiling of R1234yf. A total of 339 experimental data points sourced from the literatur...

Full description

Saved in:
Bibliographic Details
Main Authors: Farzaneh Abolhasani, Behrang Sajadi, Mohammad Ali Akhavan-Behabadi
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:International Journal of Thermofluids
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666202725001661
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849700719818440704
author Farzaneh Abolhasani
Behrang Sajadi
Mohammad Ali Akhavan-Behabadi
author_facet Farzaneh Abolhasani
Behrang Sajadi
Mohammad Ali Akhavan-Behabadi
author_sort Farzaneh Abolhasani
collection DOAJ
description In the present study, the utilization of machine learning algorithms (MLAs) is proposed for the prediction of the heat transfer coefficient and pressure drop in horizontal, vertical, and inclined tubes during flow boiling of R1234yf. A total of 339 experimental data points sourced from the literature are employed to develop and train four methods of MLAs, including the multi-layer perceptron (MLP) neural network, support vector regression (SVR), random forest, and adaptive boosting (AdaBoost). Inclination angle, mass velocity, vapor quality, and heat flux are used as input variables, while the corresponding heat transfer coefficient and pressure drop are considered as the output variables. According to the results obtained in the prediction of the heat transfer coefficient, AdaBoost model performs the best with the mean absolute percentage error (MAPE) of 5.73 % and correlation coefficient (R) of 0.979 on the test dataset. In the case of pressure drop prediction, MLP neural network shows the best performance with MAPE of 7.62 % and R of 0.990. In addition, the remarkable effect of using machine learning methods in improving prediction accuracy is demonstrated by comparing the results of MLAs with the predictions derived from some widely recognized empirical correlations.
format Article
id doaj-art-421e7c326e554aa69870baac4a96fbfa
institution DOAJ
issn 2666-2027
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series International Journal of Thermofluids
spelling doaj-art-421e7c326e554aa69870baac4a96fbfa2025-08-20T03:18:11ZengElsevierInternational Journal of Thermofluids2666-20272025-05-012710121910.1016/j.ijft.2025.101219Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniquesFarzaneh Abolhasani0Behrang Sajadi1Mohammad Ali Akhavan-Behabadi2School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, IranCorresponding author.; School of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, IranSchool of Mechanical Engineering, College of Engineering, University of Tehran, Tehran, IranIn the present study, the utilization of machine learning algorithms (MLAs) is proposed for the prediction of the heat transfer coefficient and pressure drop in horizontal, vertical, and inclined tubes during flow boiling of R1234yf. A total of 339 experimental data points sourced from the literature are employed to develop and train four methods of MLAs, including the multi-layer perceptron (MLP) neural network, support vector regression (SVR), random forest, and adaptive boosting (AdaBoost). Inclination angle, mass velocity, vapor quality, and heat flux are used as input variables, while the corresponding heat transfer coefficient and pressure drop are considered as the output variables. According to the results obtained in the prediction of the heat transfer coefficient, AdaBoost model performs the best with the mean absolute percentage error (MAPE) of 5.73 % and correlation coefficient (R) of 0.979 on the test dataset. In the case of pressure drop prediction, MLP neural network shows the best performance with MAPE of 7.62 % and R of 0.990. In addition, the remarkable effect of using machine learning methods in improving prediction accuracy is demonstrated by comparing the results of MLAs with the predictions derived from some widely recognized empirical correlations.http://www.sciencedirect.com/science/article/pii/S2666202725001661Machine learning algorithmsFlow boilingHeat transfer coefficientPressure dropR1234yf
spellingShingle Farzaneh Abolhasani
Behrang Sajadi
Mohammad Ali Akhavan-Behabadi
Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
International Journal of Thermofluids
Machine learning algorithms
Flow boiling
Heat transfer coefficient
Pressure drop
R1234yf
title Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
title_full Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
title_fullStr Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
title_full_unstemmed Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
title_short Prediction of R1234yf flow boiling behavior in horizontal, vertical, and inclined tubes using machine learning techniques
title_sort prediction of r1234yf flow boiling behavior in horizontal vertical and inclined tubes using machine learning techniques
topic Machine learning algorithms
Flow boiling
Heat transfer coefficient
Pressure drop
R1234yf
url http://www.sciencedirect.com/science/article/pii/S2666202725001661
work_keys_str_mv AT farzanehabolhasani predictionofr1234yfflowboilingbehaviorinhorizontalverticalandinclinedtubesusingmachinelearningtechniques
AT behrangsajadi predictionofr1234yfflowboilingbehaviorinhorizontalverticalandinclinedtubesusingmachinelearningtechniques
AT mohammadaliakhavanbehabadi predictionofr1234yfflowboilingbehaviorinhorizontalverticalandinclinedtubesusingmachinelearningtechniques